CVE-2026-18236
A vulnerability in the Agent Development Kit (ADK) allows for continuation forgery in tool confirmations. An attacker who is able to manipulate or inject events into the session history can execute unauthorized tools by forging a tool confirmation response. This is possible because the framework did not verify if the target tool was registered to the executing agent, did not validate if the tool actually required confirmation, and did not match the confirmation arguments against the original tool call event in the history.
CVSS
- Version: 4.0
- Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
- Base score: 9.3
Exploitation probability (EPSS)
- Probability of exploitation in the next 30 days: 0.22%
- Percentile among all scored CVEs: 11
- Score date: 10/6/2026
EPSS (Exploit Prediction Scoring System, FIRST) estimates how likely a vulnerability is to be exploited in the wild within 30 days. It complements CVSS (impact) and CISA KEV (confirmed exploitation).
🎯 ATT&CK techniques
How this vulnerability is exploited and what the attacker gains, in MITRE ATT&CK terms.
- Exploitation
T1190Exploit Public-Facing Applicationinitial access85 % - Primary impact
T1078Valid Accountsstealth · persistence · privilege escalation · initial access80 % - Secondary impact
T1059Command and Scripting Interpreterexecution75 %
AV:N/AC:L/PR:N sin UI indica explotación remota sin privilegios (T1190). La manipulación de confirmaciones de herramientas no validadas permite suplantación de identidad (T1078) y ejecución no autorizada de comandos (T1059).
Inferred by our analysis agent from the official description, CVSS vector and CWE, and checked by a supervisor. May contain errors.
🛡️ ATT&CK mitigations that cover these techniques
Affected technologies (1)
⚠ AI-inferred from the description — NVD hasn't analyzed this CVE yet, these aren't verified CPEs.
CWEs
- CWE-863
References
Raw JSON (NVD)
Show
{
"id": "CVE-2026-18236",
"cveTags": [],
"metrics": {
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-18236",
"role": "CISA Coordinator",
"options": [
{
"exploitation": "none"
},
{
"automatable": "yes"
},
{
"technicalImpact": "total"
}
],
"version": "2.0.3",
"timestamp": "2026-07-29T18:08:28.435061Z"
}
}
],
"cvssMetricV40": [
{
"type": "Secondary",
"source": "cve-coordination@google.com",
"cvssData": {
"Safety": "NOT_DEFINED",
"version": "4.0",
"Recovery": "NOT_DEFINED",
"baseScore": 9.3,
"Automatable": "NOT_DEFINED",
"attackVector": "NETWORK",
"baseSeverity": "CRITICAL",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
"exploitMaturity": "PROOF_OF_CONCEPT",
"providerUrgency": "NOT_DEFINED",
"userInteraction": "NONE",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"privilegesRequired": "NONE",
"subIntegrityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"subAvailabilityImpact": "HIGH",
"vulnAvailabilityImpact": "HIGH",
"availabilityRequirement": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"subConfidentialityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"confidentialityRequirement": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"vulnerabilityResponseEffort": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED"
}
}
]
},
"affected": [
{
"source": "cve-coordination@google.com",
"affectedData": [
{
"vendor": "Google",
"product": "Google-ADK",
"versions": [
{
"status": "affected",
"version": "< 2.5.0"
}
],
"platforms": [
"Python"
],
"defaultStatus": "unaffected"
}
]
}
],
"published": "2026-07-29T18:16:52.140",
"references": [
{
"url": "https://github.com/google/adk-python/commit/c03f333769feaeaa9fe8910fbe95cb9f2d513f54",
"source": "cve-coordination@google.com"
}
],
"vulnStatus": "Awaiting Analysis",
"weaknesses": [
{
"type": "Secondary",
"source": "cve-coordination@google.com",
"description": [
{
"lang": "en",
"value": "CWE-863"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A vulnerability in the Agent Development Kit (ADK) allows for continuation forgery in tool confirmations. An attacker who is able to manipulate or inject events into the session history can execute unauthorized tools by forging a tool confirmation response. This is possible because the framework did not verify if the target tool was registered to the executing agent, did not validate if the tool actually required confirmation, and did not match the confirmation arguments against the original tool call event in the history."
}
],
"lastModified": "2026-07-30T14:15:31.167",
"sourceIdentifier": "cve-coordination@google.com"
}